CISPA
Browse
cispa_all_2913.pdf (1.61 MB)

We Are Not Your Real Parents: Telling Causal from Confounded using MDL

Download (1.61 MB)
conference contribution
posted on 2023-11-29, 18:10 authored by David Kaltenpoth, Jilles VreekenJilles Vreeken
Given data over variables (X1,...,Xm,Y) we consider the problem of finding out whether X jointly causes Y or whether they are all confounded by an unobserved latent variable Z. To do so, we take an information-theoretic approach based on Kolmogorov complexity. In a nutshell, we follow the postulate that first encoding the true cause, and then the effects given that cause, results in a shorter description than any other encoding of the observed variables. The ideal score is not computable, and hence we have to approximate it. We propose to do so using the Minimum Description Length (MDL) principle. We compare the MDL scores under the models where X causes Y and where there exists a latent variables Z confounding both X and Y and show our scores are consistent. To find potential confounders we propose using latent factor modeling, in particular, probabilistic PCA (PPCA). Empirical evaluation on both synthetic and real-world data shows that our method, CoCa, performs very well -- even when the true generating process of the data is far from the assumptions made by the models we use. Moreover, it is robust as its accuracy goes hand in hand with its confidence.

History

Preferred Citation

David Kaltenpoth and Jilles Vreeken. We Are Not Your Real Parents: Telling Causal from Confounded using MDL. In: SIAM International Conference on Data Mining (SDM). 2019.

Primary Research Area

  • Empirical and Behavioral Security

Name of Conference

SIAM International Conference on Data Mining (SDM)

Legacy Posted Date

2019-06-07

Open Access Type

  • Unknown

BibTeX

@inproceedings{cispa_all_2913, title = "We Are Not Your Real Parents: Telling Causal from Confounded using MDL", author = "Kaltenpoth, David and Vreeken, Jilles", booktitle="{SIAM International Conference on Data Mining (SDM)}", year="2019", }

Usage metrics

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC